himadripal commented on code in PR #9803:
URL: https://github.com/apache/iceberg/pull/9803#discussion_r1509447610
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java:
##########
@@ -1463,6 +1465,130 @@ public void testSnapshotProperty() {
assertThat(table.currentSnapshot().summary()).containsKeys(commitMetricsKeys);
}
+ @Test
+ public void testBinPackRewriterWithSpecificUnparitionedOutputSpec() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .binPack()
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testBinPackRewriterWithSpecificOutputSpec() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .binPack()
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testBinpackRewriteWithInvalidOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ Assertions.assertThatThrownBy(
+ () ->
+ actions()
+ .rewriteDataFiles(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(1234))
+ .binPack()
+ .execute())
+ .isInstanceOf(IllegalArgumentException.class)
+ .hasMessage(
+ "Cannot use output spec id 1234 because the table does not contain
a reference to this spec-id.");
+ }
+
+ @Test
+ public void testSortRewriterWithSpecificOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+
.sort(SortOrder.builderFor(table.schema()).asc("c2").asc("c3").build())
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testZOrderRewriteWithSpecificOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .zOrder("c2", "c3")
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ protected void shouldRewriteDataFilesWithPartitionSpec(Table table, int
outputSpecId) {
+ List<DataFile> rewrittenFiles = currentDataFiles(table);
+ assertThat(rewrittenFiles).allMatch(file -> file.specId() == outputSpecId);
+ assertThat(rewrittenFiles)
+ .allMatch(
+ file ->
+ ((PartitionData) file.partition())
+ .getPartitionType()
Review Comment:
line 1577 - has specId() check.
```java
assertThat(rewrittenFiles).allMatch(file -> file.specId() == outputSpecId);
```
do you suggest to only have specId() check and remove the partitionType
check.?
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java:
##########
@@ -1463,6 +1465,130 @@ public void testSnapshotProperty() {
assertThat(table.currentSnapshot().summary()).containsKeys(commitMetricsKeys);
}
+ @Test
+ public void testBinPackRewriterWithSpecificUnparitionedOutputSpec() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .binPack()
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testBinPackRewriterWithSpecificOutputSpec() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .binPack()
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testBinpackRewriteWithInvalidOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ Assertions.assertThatThrownBy(
+ () ->
+ actions()
+ .rewriteDataFiles(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(1234))
+ .binPack()
+ .execute())
+ .isInstanceOf(IllegalArgumentException.class)
+ .hasMessage(
+ "Cannot use output spec id 1234 because the table does not contain
a reference to this spec-id.");
+ }
+
+ @Test
+ public void testSortRewriterWithSpecificOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+
.sort(SortOrder.builderFor(table.schema()).asc("c2").asc("c3").build())
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ @Test
+ public void testZOrderRewriteWithSpecificOutputSpecId() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+ int outputSpecId = table.spec().specId();
+ table.updateSpec().addField(Expressions.bucket("c3", 2)).commit();
+
+ long dataSizeBefore = testDataSize(table);
+ long count = currentData().size();
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .option(RewriteDataFiles.OUTPUT_SPEC_ID,
String.valueOf(outputSpecId))
+ .option(SizeBasedFileRewriter.REWRITE_ALL, "true")
+ .zOrder("c2", "c3")
+ .execute();
+
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ assertThat(currentData().size()).isEqualTo(count);
+ shouldRewriteDataFilesWithPartitionSpec(table, outputSpecId);
+ }
+
+ protected void shouldRewriteDataFilesWithPartitionSpec(Table table, int
outputSpecId) {
+ List<DataFile> rewrittenFiles = currentDataFiles(table);
+ assertThat(rewrittenFiles).allMatch(file -> file.specId() == outputSpecId);
+ assertThat(rewrittenFiles)
+ .allMatch(
+ file ->
+ ((PartitionData) file.partition())
+ .getPartitionType()
Review Comment:
do you suggest to only have specId() check and remove the partitionType
check.?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
